flukes-nlp/ner-english-8class

English named entity recognition (8 classes)

The default English NER model for Flukes. It finds and classifies named entities in English text.

F1-Score: 95.05 (measured on a held-out portion of a non-public training corpus)

⚠️ Noncommercial use only. This model is released under the Flukes NC 1.0 License. Commercial use, including using this model's predictions in a commercial product or service, requires a separate license. Contact alan.akbik@gmail.com.

Predicts 8 entity types:

label	meaning
PER	person name
LOC	location name
ORG	organization name
PRODUCT	product name ("Oura Ring 5")
WORK_OF_ART	film/song/album/book name
EVENT	named event ("1970 World Cup")
IDENT	nationality, ethnicity, regional or religious affiliation
MISC	other name

Usage

Requires Flukes (pip install flukes).

from flukes.models import Model

# load the NER model
model = Model.load("ner")

# predict for an example sentence
doc = model.predict("Santos star Pelé won the 1970 World Cup in Mexico.")

# iterate over found entities
for span in doc.get_spans("ner"):
    print(span)

This prints:

Span[0:6]: "Santos" → ORG ⟨ner⟩ 0.95
Span[12:16]: "Pelé" → PER ⟨ner⟩ 1.00
Span[25:39]: "1970 World Cup" → EVENT ⟨ner⟩ 1.00
Span[43:49]: "Mexico" → LOC ⟨ner⟩ 1.00

License

Model weights: Flukes Noncommercial License 1.0. Personal, academic and other noncommercial use is permitted. Commercial use requires a separate license; contact alan.akbik@gmail.com.